© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48282
    Prev
    Next
    INDEX
    Explanations

    unaffected activities despite disruptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lashes
    -0.09
    aldo
    -0.09
     encompass
    -0.09
     Rocks
    -0.09
     #__
    -0.09
    963
    -0.09
    964
    -0.09
    ctl
    -0.09
     felony
    -0.09
     Pension
    -0.09
    POSITIVE LOGITS
     normal
    0.23
     Normal
    0.18
     usual
    0.17
     scheduled
    0.17
     unaffected
    0.17
     activities
    0.16
     functioning
    0.16
     travel
    0.16
    normal
    0.16
    Normal
    0.16
    Activations Density 0.576%

    No Known Activations